CN104391654B - A kind of shared disk management method and system - Google Patents
A kind of shared disk management method and system Download PDFInfo
- Publication number
- CN104391654B CN104391654B CN201410637110.9A CN201410637110A CN104391654B CN 104391654 B CN104391654 B CN 104391654B CN 201410637110 A CN201410637110 A CN 201410637110A CN 104391654 B CN104391654 B CN 104391654B
- Authority
- CN
- China
- Prior art keywords
- node device
- disk
- disk unit
- business
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007726 management method Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000013500 data storage Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/062—Securing storage systems
Abstract
The present invention provides a kind of shared disk management method and system, the above method comprise the following steps：General unique identifier UUID is set for disk unit in advance；The disk unit then shields other node device carries requests by node device carry and when providing service；After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment is according to default Selection Strategy, the selection target node device from other node devices.The present invention realizes the unique mark of shared disk equipment in cluster, while ensure that Information Security and service continuity in shared disk equipment, the problem of effectively prevent corrupted data.
Description
Technical field
The invention belongs to disk management field, more particularly to a kind of shared disk management method and system.
Background technology
In present cluster-based storage, shared disk has been a kind of relatively common high availability implementation method, but shared
Disk is in the cluster in use, presence carry, while provide service simultaneously, causes the situation of corrupted data, how to avoid sharing
This problem of disk, ensure the security of data, the problem of being particularly significant.
The content of the invention
The present invention provides a kind of shared disk management method and system, to solve the above problems.
The present invention provides a kind of shared disk management method.The above method comprises the following steps：
General unique identifier UUID is set for disk unit in advance；
The disk unit then shields other node device carries requests by node device carry and when providing service；
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment according to
Default Selection Strategy, the selection target node device from other node devices.
The present invention also provides a kind of shared disk management system, including disk unit, multiple node devices, disk management are set
It is standby；Wherein, the disk unit is connected with multiple node devices respectively；The disk management equipment is set with the disk respectively
Standby, the multiple node device is connected；
General unique identifier UUID is set for disk unit in advance；
The disk unit, for by node device carry and when providing service, shielding other node device carries requests；
The node device, after having used the disk unit, trigger notice is sent to disk management equipment；
Disk management equipment, after the trigger notice sent for receiving the node device, according to default Selection Strategy,
The selection target node device from other node devices.
It is in advance disk according to a kind of shared disk management method provided by the invention and system compared to prior art
Equipment sets general unique identifier UUID；The disk unit then shields other by node device carry and when providing service
Node device carry is asked；After if the node device of disk unit described in carry has used the disk unit, trigger disk pipe
Equipment is managed according to default Selection Strategy, the selection target node device from other node devices.Realize and magnetic is shared in cluster
The unique mark of disc apparatus, while Information Security and service continuity in shared disk equipment are ensure that, it effectively prevent number
The problem of according to damage.
Pass through following scheme：After if the node device of disk unit described in carry has used the disk unit, trigger magnetic
Disk management equipment asks the type of service and type of service and business importance coefficient vs table of processing according to node device, it is determined that
The business importance coefficient of node device request processing；According to node device magnetic disc access times and magnetic disc access times scope with
Disk access coefficient vs table, determine node device disk access coefficient；According to the business importance of node device request processing
Coefficient, node device disk access coefficient, determine the matching degree of node device；Matching degree highest node device is selected as mesh
Mark node device.It ensure that the node device of processing important service obtains priority treatment so that system resource is utilized effectively.
Pass through following scheme：The disk unit is by node device carry and when providing service, if the node device is sent out
Failure is given birth to, then the disk unit is switched to other node devices by disk management equipment.Realize shared disk equipment carry
The switching in cluster is serviced, ensure that business processing continuity, security.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, forms the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 show the shared disk management method flow chart of the embodiment of the present invention 1；
Fig. 2 show the shared disk management system structure diagram of the embodiment of the present invention 2.
Embodiment
Describe the present invention in detail below with reference to accompanying drawing and in conjunction with the embodiments.It should be noted that do not conflicting
In the case of, the feature in embodiment and embodiment in the application can be mutually combined.
Fig. 1 show the shared disk management method flow chart of the embodiment of the present invention 1, comprises the following steps：
Step 101：General unique identifier UUID is set for disk unit in advance；
Indicated by UUID (Universal ly Unique Ident ifier, general unique identifier) in cluster
Unique disk unit.Unique disk unit in cluster is indicated by UUID, that is, with UUID come Replace Disk and Press Anykey To Reboot equipment
Title, with UUID uniqueness mark disk unit, so that it is guaranteed that disk unit is unique in cluster, distinguish mutually not
Same disk unit.
Step 102：The disk unit then shields other node device carries by node device carry and when providing service
Request；
If the disk unit by some node device carry and to the node device provide service when, other node devices
Carry request is sent to the disk unit, then the disk unit feeds back carry failure response to other node devices.So
Just protect the disk unit for providing service unaffected, avoid the occurrence of to multiple node devices while the feelings of service are provided
Condition, avoids producing that data are inconsistent or the situation of corrupted data.
The disk unit is by node device carry and when providing service, if the node device breaks down, disk
The disk unit is switched to other node devices by management equipment.
Such as：The disk unit is by the carry of node device 1 and when providing service, if the node device 1 breaks down,
Then the disk unit is switched to node device 2 by disk management equipment.
Step 103：After if the node device of disk unit described in carry has used the disk unit, trigger disk management
Equipment is according to default Selection Strategy, the selection target node device from other node devices；
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment according to
Default Selection Strategy, the process of selection target node device is from other node devices：
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment according to
Node device priority, the selection target node device from other node devices.
Such as：If there are three node devices (node device 1, node device 2, node device 3)；Wherein, node device 1
Priority is more than node device 2；The priority of node device 2 is more than node device 3.
It is preferential due to node device 2 after if the node device 1 of disk unit described in carry has used the disk unit
Level is more than node device 3, then it is target node device to select node device 2.
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment according to
Default Selection Strategy, the process of selection target node device is from other node devices：
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment according to
The business operation order of each node request processing, the selection target node device from other node devices.
Such as：If there are three node devices (node device 1, node device 2, node device 3)；At the request of node device 2
The business of reason is data encryption, the business of the request processing of node device 3 is data storage.Because data storage operations need
Before, data encryption operation is needed rear, therefore selects node device 3 to be used as target node device.
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment according to
Default Selection Strategy, the process of selection target node device is from other node devices：
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment according to
The type of service and type of service and business importance coefficient vs table of node device request processing, are determined at node device request
The business importance coefficient of reason；
According to node device magnetic disc access times and magnetic disc access times scope and disk access coefficient vs table, it is determined that section
Point device disk access coefficient；
According to business importance coefficient, the node device disk access coefficient of node device request processing, determine that node is set
Standby matching degree；
Matching degree highest node device is selected as target node device.
Business importance coefficient/node device disk access system of node device matching degree=node device request processing
Number.
Type of service and business importance coefficient vs table
| Type of service | Business importance coefficient |
| Data encryption business | 1 |
| Operational data storage | 0.8 |
| Data more new business | 0.6 |
Table 1
Magnetic disc access times scope and disk access coefficient vs table
| Magnetic disc access times (X) scope | Disk access coefficient |
| 50 ＜ X≤100 | 1.0 |
| 10 ＜ X≤50 | 0.8 |
| X ＜ 10 | 0.6 |
Table 2
Preset period of time according to actual conditions need carry out flexibly setting (such as：1 minute), the restriction present invention is not used in herein
Protection domain.
If there are three node devices (node device 1, node device 2, node device 3)；If disk unit described in carry
After node device 1 has used the disk unit, it is data encryption that node device 2, which asks the business of processing, node device 3 is asked
The business of processing is data storage；Then the business importance coefficient of the request processing of node device 2 is 1, at the request of node device 3
The business importance coefficient of reason is 0.8；
If the magnetic disc access times of node device 2 are 10 times；3 magnetic disc access times of node device 12 times, then node device 2
Disk access coefficient is 0.6；The disk access coefficient of node device 3 is 0.8.
Then business importance coefficient/disk of node device 2 of the request of 2 matching degrees of node device=node device 2 processing is visited
Ask coefficient=1/0.6=1.67；Business importance coefficient/node of the request processing of 3 matching degrees of node device=node device 3 is set
Standby 3 disk access coefficients=0.8/0.8=1.
Then selection selection matching degree highest node device 2 is used as target node device.
Step 104：The target node device sends carry request to the disk unit；
Step 105：The disk unit receives the carry request and provides service to the target node device.
Fig. 2 show the shared disk management system structure diagram of the embodiment of the present invention 2, including disk unit, node device
1st, node device 2, node device 3, disk management equipment；Wherein, the disk unit respectively with node device 1, node device
2nd, node device 3 is connected；The disk management equipment respectively with the disk unit, the node device 1, node device 2, section
Point device 3 is connected；
General unique identifier UUID is set for disk unit in advance；
The disk unit, for by the carry of node device 1 and when providing service, masked nodes equipment 2, node device 3
Carry request；
The node device 1, after having used the disk unit, trigger notice is sent to disk management equipment；
Disk management equipment, after the trigger notice sent for receiving the node device 1, according to default selection plan
Slightly, the selection target node device from node device 2, node device 3.
It is in advance disk according to a kind of shared disk management method provided by the invention and system compared to prior art
Equipment sets general unique identifier UUID；The disk unit then shields other by node device carry and when providing service
Node device carry is asked；After if the node device of disk unit described in carry has used the disk unit, trigger disk pipe
Equipment is managed according to default Selection Strategy, the selection target node device from other node devices.Realize and magnetic is shared in cluster
The unique mark of disc apparatus, while Information Security and service continuity in shared disk equipment are ensure that, it effectively prevent number
The problem of according to damage.
Pass through following scheme：After if the node device of disk unit described in carry has used the disk unit, trigger magnetic
Disk management equipment asks the type of service and type of service and business importance coefficient vs table of processing according to node device, it is determined that
The business importance coefficient of node device request processing；According to node device magnetic disc access times and magnetic disc access times scope with
Disk access coefficient vs table, determine node device disk access coefficient；According to the business importance of node device request processing
Coefficient, node device disk access coefficient, determine the matching degree of node device；Matching degree highest node device is selected as mesh
Mark node device.It ensure that the node device of processing important service obtains priority treatment so that system resource is utilized effectively.
Pass through following scheme：The disk unit is by node device carry and when providing service, if the node device is sent out
Failure is given birth to, then the disk unit is switched to other node devices by disk management equipment.Realize shared disk equipment carry
The switching in cluster is serviced, ensure that business processing continuity, security.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (9)
1. a kind of shared disk management method, it is characterised in that comprise the following steps：
General unique identifier UUID is set for disk unit in advance；
The disk unit then shields other node device carries requests by node device carry and when providing service；
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment is according to default
Selection Strategy, the selection target node device from other node devices；
Wherein, the default Selection Strategy includes：According to selection node device matching degree selection target node device, the section
Business importance coefficient/node device disk access coefficient of point device matching degree=node device request processing；
The business importance coefficient is relevant with type of service, and type of service comprises at least data encryption business, data storage industry
Business and data renewal business, the business importance coefficient of data encryption business>The business importance coefficient of operational data storage>Number
According to the business importance coefficient of more new business；
The disk access coefficient is according to node device magnetic disc access times, from the magnetic disc access times scope and magnetic pre-set
Disk is accessed to inquire about in coefficient vs relation and determined.
2. according to the method for claim 1, it is characterised in that：If the disk unit by some node device carry and to
The node device provide service when, other node devices to the disk unit send carry request, then the disk unit to
Other node devices feed back carry failure response.
3. according to the method for claim 1, it is characterised in that：The default Selection Strategy also includes：Set according to node
Standby priority selection target node device.
4. according to the method for claim 1, it is characterised in that：The default Selection Strategy also includes：
According to the business operation sequential selection target node device of each node request processing.
5. according to the method for claim 1, it is characterised in that：It is described according to selection node device matching degree selection target section
The also included process of point device is：
After if the node device of disk unit described in carry has used the disk unit, triggering disk management equipment is according to node
The type of service and type of service and business importance coefficient vs table of device request processing, determine node device request processing
Business importance coefficient；
According to node device magnetic disc access times and magnetic disc access times scope and disk access coefficient vs table, determine that node is set
Standby disk access coefficient；
According to business importance coefficient, the node device disk access coefficient of node device request processing, node device is determined
Matching degree；
Matching degree highest node device is selected as target node device.
6. according to the method for claim 1, it is characterised in that：If the node device of disk unit described in carry has used institute
After stating disk unit, triggering disk management equipment is according to default Selection Strategy, the selection target node from other node devices
After equipment, the target node device sends carry request to the disk unit.
7. according to the method for claim 6, it is characterised in that：The disk unit receives the carry request and to described
Target node device provides service.
8. according to the method for claim 1, it is characterised in that：The disk unit is by node device carry and provides service
When, if the node device breaks down, the disk unit is switched to other node devices by disk management equipment.
9. a kind of shared disk management method, it is characterised in that including disk unit, multiple node devices, disk management equipment；
Wherein, the disk unit is connected with multiple node devices respectively；The disk management equipment respectively with the disk unit, institute
Multiple node devices are stated to be connected；
General unique identifier UUID is set for disk unit in advance；
The disk unit, for by node device carry and when providing service, shielding other node device carries requests；
The node device, after having used the disk unit, trigger notice is sent to disk management equipment；
Disk management equipment, after the trigger notice sent for receiving the node device, according to default Selection Strategy, from it
Selection target node device in its node device；
Wherein, the default Selection Strategy includes：According to selection node device matching degree selection target node device, the section
Business importance coefficient/node device disk access coefficient of point device matching degree=node device request processing；
The business importance coefficient is relevant with type of service, and type of service comprises at least data encryption business, data storage industry
Business and data renewal business, the business importance coefficient of data encryption business>The business importance coefficient of operational data storage>Number
According to the business importance coefficient of more new business；
The disk access coefficient is according to node device magnetic disc access times, from the magnetic disc access times scope and magnetic pre-set
Disk is accessed to inquire about in coefficient vs relation and determined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410637110.9A CN104391654B (en) | 2014-11-06 | 2014-11-06 | A kind of shared disk management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410637110.9A CN104391654B (en) | 2014-11-06 | 2014-11-06 | A kind of shared disk management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104391654A CN104391654A (en) | 2015-03-04 |
| CN104391654B true CN104391654B (en) | 2018-02-06 |
Family
ID=52609565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410637110.9A Active CN104391654B (en) | 2014-11-06 | 2014-11-06 | A kind of shared disk management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104391654B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104731915B (en) * | 2015-03-24 | 2019-03-22 | 上海爱数信息技术股份有限公司 | Disk unit mapping method in a kind of distributed memory system |
| CN106817399A (en) * | 2015-12-02 | 2017-06-09 | 中兴通讯股份有限公司 | Virtual network hard disk hanging method, LAN server, user terminal and system |
| CN106681799B (en) * | 2017-01-03 | 2018-05-18 | 北京百度网讯科技有限公司 | It is inserted into the methods, devices and systems of disk |
| CN111444157B (en) * | 2019-01-16 | 2023-06-20 | 阿里巴巴集团控股有限公司 | Distributed file system and data access method |
| CN110333972A (en) * | 2019-07-03 | 2019-10-15 | 深信服科技股份有限公司 | Shared disk management method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599978A (en) * | 2009-07-17 | 2009-12-09 | 杭州华三通信技术有限公司 | Resource allocation methods and equipment |
| CN102298539A (en) * | 2011-06-07 | 2011-12-28 | 华东师范大学 | Method and system for scheduling shared resources subjected to distributed parallel treatment |
| CN102868754A (en) * | 2012-09-26 | 2013-01-09 | 北京联创信安科技有限公司 | High-availability method, node device and system for achieving cluster storage |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2413434A1 (en) * | 2000-06-26 | 2002-01-03 | International Business Machines Corporation | Data management application programming interface for a parallel file system |
| JP4561283B2 (en) * | 2004-09-30 | 2010-10-13 | ブラザー工業株式会社 | Node device, shared information update method, shared information storage method, shared information update processing program, and shared information storage processing program |
| CN102339283A (en) * | 2010-07-20 | 2012-02-01 | 中兴通讯股份有限公司 | Access control method for cluster file system and cluster node |
-
2014
- 2014-11-06 CN CN201410637110.9A patent/CN104391654B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599978A (en) * | 2009-07-17 | 2009-12-09 | 杭州华三通信技术有限公司 | Resource allocation methods and equipment |
| CN102298539A (en) * | 2011-06-07 | 2011-12-28 | 华东师范大学 | Method and system for scheduling shared resources subjected to distributed parallel treatment |
| CN102868754A (en) * | 2012-09-26 | 2013-01-09 | 北京联创信安科技有限公司 | High-availability method, node device and system for achieving cluster storage |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104391654A (en) | 2015-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104391654B (en) | A kind of shared disk management method and system | |
| CN108009261B (en) | Data synchronization method and device and electronic equipment | |
| CN102982141B (en) | A kind of method and device realizing distributed data base agency | |
| CN108897628A (en) | A kind of implementation method of distributed lock, device and electronic equipment | |
| US10235047B2 (en) | Memory management method, apparatus, and system | |
| CN108829738B (en) | Data storage method and device in ceph | |
| EP3553647A1 (en) | Data write method, apparatus, and system | |
| CN102929220A (en) | Distributed monitoring system and database server, fault processing device and fault processing method thereof | |
| CN110244901B (en) | Task allocation method and device and distributed storage system | |
| WO2020133963A1 (en) | Blockchain-based data storage method, related device and storage medium | |
| CN111355600B (en) | Main node determining method and device | |
| CN105631023A (en) | Method and device for distribution type lock service | |
| CN105635320A (en) | Method and equipment for calling configuration information | |
| CN103905232A (en) | Virtual-machine management system and method | |
| CN107341056A (en) | A kind of method and device of the thread distribution based on NFS | |
| DE102012218436A1 (en) | Distribute Licensed Content to Multiple Units | |
| CN111026761B (en) | Financial data storage system, processing method and device | |
| CN106250487A (en) | A kind of database concurrency control method and device | |
| CN104272273A (en) | Dynamic memory allocation | |
| US9826043B2 (en) | Method to protect storage systems from discontinuity due to device misconfiguration | |
| CN105183375B (en) | A kind of control method and device of the service quality of hot spot data | |
| CN107682205A (en) | On-line message dissemination method, device and electronic equipment | |
| WO2020133962A1 (en) | Blockchain-based data storage method, related device and storage medium | |
| CN105472628B (en) | Extend the method and device of WLAN ID numbers | |
| CN108429780B (en) | Data calling system and method between associated systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |